arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.07974cs.CL
收藏

自然语言和数学语言的树型表示与生成

Tree-Based Representation and Generation of Natural and Mathematical Language

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Alexander Scarlatos, Andrew Lan

摘要:

数学语言在科学交流和教育场景中很重要,但与自然语言相比,研究相对不足。数学语言的最新研究集中在表示独立的数学表达式,特别是在它们的自然树格式中,或者在预先训练的自然语言模型中进行数学推理。关于联合建模和生成自然语言和数学语言的现有工作简单地将数学表达式视为文本,而没有考虑数学表达式的刚性结构属性。在本文中,我们提出了一系列的修改现有的语言模型,共同表示和生成文本和数学:表示数学表达式的节点令牌在其操作符树格式的序列,使用数学符号和树位置嵌入,以保持语义和结构属性的数学表达式,并使用约束解码方法来生成数学上有效的表达式。我们在GPT-2的基础上进行修改,得到一个模型MathGPT,并证明它在数学表达式生成任务上优于基线。

英文摘要:

Mathematical language in scientific communications and educational scenarios is important yet relatively understudied compared to natural languages. Recent works on mathematical language focus either on representing stand-alone mathematical expressions, especially in their natural tree format, or mathematical reasoning in pre-trained natural language models. Existing works on jointly modeling and generating natural and mathematical languages simply treat mathematical expressions as text, without accounting for the rigid structural properties of mathematical expressions. In this paper, we propose a series of modifications to existing language models to jointly represent and generate text and math: representing mathematical expressions as sequences of node tokens in their operator tree format, using math symbol and tree position embeddings to preserve the semantic and structural properties of mathematical expressions, and using a constrained decoding method to generate mathematically valid expressions. We ground our modifications in GPT-2, resulting in a model MathGPT, and demonstrate that it outperforms baselines on mathematical expression generation tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑